IJIRST International Journal for Innovative Research in Science & Technology| Volume 2 | Issue 02 | July 2015

ISSN (online): 2349-6010

Intellectual Wireless Communication System by

Cognitive Radio
S. Sidhardha
Department of Electronics and Communication Engineering
Prathyusha Engineering College

L. Manisankar Reddy
Department of Electronics and Communication Engineering
Prathyusha Engineering College

S. Padmaja
Department of Electronics and Electrical Engineering
Sri Venkateswara Eng College for women

N. Ravi Teja
Department of Electronics and Communication Engineering
RVR&Jc College of engineering

N. Govinda Rao
Department of Electronics and Communication Engineering
RVR&Jc College of engineering

Abstract
The growth for wireless communication introduces competent spectrum operation challenge. To tackle this challenge, cognitive
radio (CR) is emerged as the key technology; which enables opportunistic access to the spectrum. CR is a shape of wireless
communication in which a transceiver can intelligently detect which communication channels are in use and which are not, and
instantly move into empty channels while avoiding occupied ones. This optimizes the use of obtainable radio-frequency (RF)
spectrum while minimizing interference to other users. In this paper, we present a position of the art on the use of Multi Agent
Systems (MAS) for spectrum access using cooperation and competition to solve the problem of spectrum allocation and warrant
better management. Then we propose a new approach which uses the CR for improving wireless communication for a single
cognitive radio mobile terminal (CRMT).
Keywords: Cognitive Radio, wireless communication, mobility, multi Agent system, cognitive radio terminal
_______________________________________________________________________________________________________

I. INTRODUCTION
The Cognitive Radio (CR) this concept has been very popular with researchers in several fields such as telecommunications,
artificial intelligence, and even philosophy. Joseph Mitola has defined the CR as a radio that employs model-based reasoning to
achieve a specified level of competence in radio-related domain. Most researches on CR networks have determined on the
exploitation of unused spectrum. However, the CR nodes possess the necessary qualities to make a considerable progress in the
reliability of wireless networks, which has been less explored, so that is why we were interested by improving the wireless link
reliability of a video conferencing application. The aim of our paper is to propose a technique to improve wireless
communication to a video conferencing application for a mobile terminal using the CR for only one CRMT. For this, it seemed
appropriate to choose a scenario on which we will apply our approach. Our technique is based on machine learning. In our future
work, we will seek to improve real-time application performance related to many CRMT based on MAS.

II. SYNTHETIC INTELLIGENCE AND COGNITIVE RADIO

Artificial intelligence (AI) techniques for learning and decision making can be applied to design efficient cognitive radio
systems. The concept of machine learning was applied to CR for capacity maximization and dynamic spectrum access. Different
knowledge algorithms can be used in CR networks (Hidden Markov Model, neural networks, genetic algorithms, decision trees,
and fuzzy logic or classification algorithms).CRs need to have the ability to learn and adapt their wireless transmission according
to the ambient radio environment. intellectual algorithms such as those based on machine learning, genetic algorithms, and fuzzy
control are therefore key to the implementation of CR technology. In wide-ranging, these algorithms are used to observe the state
of the wireless environment and build knowledge about the environment. This knowledge is used by a cognitive radio to adapt its
decision on spectrum access. For example, a secondary user can observe the transmission activity of primary users on different
channels. This enables the CR to build knowledge about the primary users activity on every channel. This knowledge is then
worn by the CR to decide which channel to access so that the desired performance objectives can be achieved (e.g. throughput is
maximized while the interference or collision caused to the primary users is maintained below the target level).
A. Neural Networks
A multilayered neural network was used to model and estimate the performances of IEEE 802.11 networks. This neural network
provides a black-box model for the non-linear relationship between the inputs and the outputs. This neural network model can

All rights reserved by www.ijirst.org

254

Intellectual Wireless Communication System by Cognitive Radio

(IJIRST/ Volume 2 / Issue 02/ 043)

learn from training data which can be obtained in an on-line manner when the real-time measurement data are available.
Therefore, this moist suitable for a cognitive radio network for which a prompt response to the changing radio environment is
required from an unlicensed user.

Fig. 1: Neural Networks

B. Fuzzy Logic
Fuzzy logic is often combined with neural networks that can adapt to the environment during the evolution of a CR system. A
fuzzy logic control system can be used to obtain the solution to a problem given imprecise, noisy, and incomplete input
information. In short, instead of using complicated mathematical formulations, fuzzy logic uses human-understandable fuzzy sets
and inference rules to obtain the solution that satisfies the desired system objectives. The main gain of fuzzy logic is its low
complexity. Therefore, fuzzy logic is suitable for real-time cognitive radio applications in which the response time is critical to
system performance. In general, there are three major components in a fuzzy logic control system fuzzy logic processor, and
defuzzifier. While the fuzzifier is used to map the crisp inputs into fuzzy sets, the fuzzy logic processor implements an inference
engine to obtain the solution based on predefined sets of rules. Then, the defuzzifier is applied to transform the solution to the
crisp output.

Fig. 2: Fuzzy Logic Controller

III. MULTI AGENT SYSTEMS AND COGNITIVE RADIO

The association of MAS and the CR can provide a great future for the optimal management of frequencies (in comparison with
the rigid control techniques proposed by the telecommunications operators). In the case of use of unlicensed bands, the CR
terminal has to coordinate and cooperate to best use the spectrum without causing interferes. In, the authors propose architecture
based on agents where each CR terminal is equipped with an intelligent agent, there are modules to collect information about the
radio environment and of course the information collected will be stored in a shared knowledge base that will be accessed by all
agents. The proposed loom is based on cooperative MAS (the agents have common interests). They work by contribution of their
knowledge to increase their collective and individual gain. Agents are deployed on the PUs and SUs terminals and cooperate

All rights reserved by www.ijirst.org

255

Intellectual Wireless Communication System by Cognitive Radio

(IJIRST/ Volume 2 / Issue 02/ 043)

with each other in the works projected in. By cooperative MAS, we mean that PU agents exchanged of messages in order to
improve themselves and the neighbourhood of SU agents. They propose that the SUs should make their decision based on the
amount of available spectrum when they find a suitable offer (without waiting for response from all PUs). Agents are deployed
on the PUs and SUs terminals and cooperate with each other in the works proposed in. By cooperative MAS, we mean that PU
agents exchanged t-uples of messages in order to improve themselves and the neighbourhood of SU agents. Agents are deployed
on the PUs and SUs terminals and cooperate with each other in the works proposed in. By cooperative MAS, we mean that PU
agents exchanged t-uples of messages in order to improve themselves and the neighbourhood of SU agents. They propose that
the SUs should make their decision based on the amount of available spectrum when they find a suitable offer (without waiting
for response from all PUs). In other words, the SU agent should send messages to the appropriate neighbour PU agent and of
course the concerned PU must respond to these agents to an agreement on sharing the spectrum. After the end of the spectrum
use, the SU must pay the PU.A comparison is made in between an agent and a CR. Basically, both of them are aware of their
surrounding environments through interactions, sensing, monitoring and they have autonomy and control over their actions and
states. They can solve the assigned tasks independently based on their individual capabilities or can work with their neighbours
by having frequent information exchanges. To make the CR systems practical, it requires that several CR networks coexist with
each other. However, this can cause interference. The authors of think that to remedy this problem, the SU can cooperate to sense
the spectrum as well as to share it without causing interference to the PU. For this, they propose schemes to protect the PU from
interferences by controlling the transmission power of the cognitive terminal. Propose cooperation between PUs and SUs and
between SUs only. Agents are deployed on the users terminals to cooperate and result in contracts governing spectrum
allocation. SU agents coexist and cooperate with the PU agents in an Ad hoc CR environment using messages and mechanisms
for decision making. Since the internal behaviours of agents are cooperative and selfless, it enables them to maximize the utility
function of other agents without adding costs result in terms of exchanged messages. However, the allocation of resources is an
important issue in CR systems.

IV. QUALITY OF SERVICE IN VIDEO CONFERENCING

Quality of Service (QoS) refers to the capability of a network to provide better service to selected network traffic over various
technologies, counting Frame Relay, Asynchronous Transfer Mode (ATM), Ethernet and 802.1 networks, SONET, and IP-routed
networks that may use any or all of these original technologies. The primary goal of QoS is to provide precedence including
dedicated bandwidth, controlled jitter and latency (required by some real-time and interactive traffic), and improved loss
characteristics. Also important is making sure that providing priority for one or more flows does not make other flows fail. With
the emergence of new services such as video conferencing and video streaming, the need to treat the frames one by one and to
know how differentiate services becomes primordial. An interactive video conferencing cannot tolerate long delays because there
is not enough time to retransmit lost packets. Lost packets or very late ones are simply ignored which will cause deterioration of
images and sound. With a network that provides an acceptable throughput, we should control the delay (between the
transmission and reception of a packet), jitter (delay variation), usually this type of applications does not tolerate large jitter to
not damage the image and sound and of course we must also control the loss of images. The packet classifier in the network
device separates the arriving traffic into either distinct classes or individual application flows such that each class of traffic or
flow may be provided a different service. One looks at the explicit markings in the type of service field or the traffic class field in
IPv4 and IPv6, respectively. The other looks at numerous fields in the IP header (source IP address, source port, destination IP
address, and destination port and protocol type) to associate it with a particular applications traffic flow. Once the traffic is
classified into multiple classes, it is possible for each class of packets to receive different treatment from the device.

Fig. 3: Quality of service in video conferencing

All rights reserved by www.ijirst.org

256

Intellectual Wireless Communication System by Cognitive Radio

(IJIRST/ Volume 2 / Issue 02/ 043)

V. CONCLUSION
This paper is a new approach that uses Cognitive Radio to improve wireless communication for a cognitive radio mobile
terminal by enhancing the QoS of video conferencing application. Our contribution is positioned in learning from events
(machine learning). Our expert role has allowed us to choose the throughput parameter to perform a classification that allows the
terminal used to gain experience for future events that means that it will know when and where it will activate the cognitive
radio. The usefulness of cognitive radio is a hypothesis that has been proved based on the required time for a connection to a new
frequency band, and this, whatever of the number of frequency bands that a terminal used to remedy a unsuccessful connection.
Different approach using the MAS in the CR are studied, those offering cooperation between SUs only, others offer a
cooperation between primary and SUs.

REFERENCES
[1]
[2]
[3]
[4]
[5]
[6]

J. Mitola, (1999) Cognitive radio model-based competence for software radios, Licentiate Thesis, KTH, Stockholm.
J. Neel, (2012) Analysis and Design of Cognitive Radio Networks and Distributed Radio Resource Management Algorithms, Faculty of the Virginia
Polytechnic Institute and State University.
C. Clancy et al, (2007) Applications of machine learning to cognitive radio networks, IEEE Wireless Communications, vol. 14, no. 4.
E. hossain, D. Niyan, Zhu Han, Dynamic Spectrum Access and management in cognitive radio networks, Cambridge University Press 2009.
S. Bushnell et al, (2011) Vertical Handover between Wi-Fi and UMTS Networks: Experimental Performance Analysis, International Journal of Energy,
Information and Communications Vol. 2, Issue 1.
J. Karaoguz. High-rate wireless personal area networks. Communications Magazine, IEEE, 39(12):96102, Dec 2013.

All rights reserved by www.ijirst.org

257